Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    warmest temperatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    引进
    0.38
     Nons
    0.37
     شف
    0.37
    Moral
    0.37
    នាំ
    0.37
     প্রসঙ্গ
    0.35
     сравнению
    0.35
    hluk
    0.35
    ведение
    0.34
    イビー
    0.33
    POSITIVE LOGITS
    startTime
    0.49
     IPO
    0.48
     posicion
    0.44
     veo
    0.43
     Timing
    0.41
     titt
    0.40
    대에
    0.40
     saludo
    0.38
     timings
    0.38
     position
    0.38
    Act Density 0.000%

    No Known Activations